Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    factorization, factory, factorials, factor analysis, factory pattern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ký
    0.48
    ánicos
    0.46
    ্ের
    0.45
    ógicas
    0.43
    بانی
    0.42
     terrible
    0.40
     lacked
    0.40
    ąz
    0.39
     الطرف
    0.39
     Clancy
    0.39
    POSITIVE LOGITS
     facteurs
    0.75
     factors
    0.70
    Factors
    0.68
     factor
    0.68
     faktor
    0.68
     factores
    0.65
     fator
    0.65
     Factor
    0.64
     Factors
    0.64
     fatores
    0.64
    Act Density 0.014%

    No Known Activations